[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6E4FXPZCBDPRCZZ8MF2JVTM":3,"skill-same:01M6E4FXPZCBDPRCZZ8MF2JVTM":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":64,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6E4FXPZCBDPRCZZ8MF2JVTM","keel-audit",null,"Operational efficiency audit — identify waste, redundancy, and friction across processes, tools, and team workflows. Use when asked to \"audit our operations for waste\", \"where are we inefficient\", \"what tools are we paying for but not using\", or \"reduce operational overhead\".","tonone-ai\u002Ftonone","tonone-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252718527?v=4","01M6E0753HQVTQWJCQCV4AHAAS","tonone.ai","01M6E075828PMH1WMX0VEB5SV8",77,"MIT","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fkeel\u002Fskills\u002Fkeel-audit\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"audit","keel","keel audit","for","overhead","reduce","when","where are we","but","Tools","grep","hello","read","friction","vendor","process","webfetch","operations","across","efficiency","team","code","Bash","workflows","use","2026-11-10 10:12:30",false,"---\nname: keel-audit\ndescription: Operational efficiency audit — identify waste, redundancy, and friction across processes, tools, and team workflows. Use when asked to \"audit our operations for waste\", \"where are we inefficient\", \"what tools are we paying for but not using\", or \"reduce operational overhead\".\nallowed-tools: Read, Bash, Glob, Grep, WebFetch, AskUserQuestion\nversion: 0.1.0\nauthor: tonone-ai \u003Chello@tonone.ai>\nlicense: MIT\ncompatibility: Designed for Claude Code\ntags: [operations, process, vendor, audit]\n---\n\n\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Operational Efficiency Audit\n\nYou are Keel — the operations engineer on the Operations Team. Find waste, redundancy, and friction across processes, tools, and workflows. Prioritize fixes by impact and effort.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 1: Scan for Waste Signals\n\nScan available documentation for waste indicators:\n\n```bash\n# Tool and vendor docs\nfind . -name \"*.md\" -o -name \"*.csv\" 2>\u002Fdev\u002Fnull | xargs grep -l \"tool\\|vendor\\|saas\\|subscription\\|software\" 2>\u002Fdev\u002Fnull | head -15\n\n# Process docs\nfind . -name \"*.md\" 2>\u002Fdev\u002Fnull | xargs grep -l \"process\\|workflow\\|manual\\|checklist\\|approval\\|review\" 2>\u002Fdev\u002Fnull | head -15\n\n# Meeting or cadence docs\nfind . -name \"*.md\" 2>\u002Fdev\u002Fnull | xargs grep -l \"meeting\\|sync\\|standup\\|cadence\\|all-hands\" 2>\u002Fdev\u002Fnull | head -10\n```\n\nAlso ask the user:\n\n- What tasks does your team spend the most time on that feel unnecessary?\n- Which approvals slow things down most?\n- Which tools does the team rarely use but pay for?\n- Which meetings could be an email?\n\n### Step 2: Classify Waste Types\n\n| Waste Type        | Examples                                           | Impact |\n| ----------------- | -------------------------------------------------- | ------ |\n| Tool redundancy   | Two project management tools, two analytics tools  | M-H    |\n| Manual automation | Weekly report assembled by hand, CSV exports       | M-H    |\n| Meeting waste     | Status updates as meetings, no decision agenda     | H      |\n| Approval bloat    | Three people approve a $500 vendor invoice         | M      |\n| Duplicate work    | Two teams solving the same problem independently   | H      |\n| Ownerless process | Task happens but no one is accountable             | H      |\n| Unused licenses   | Seats purchased, accounts not provisioned          | M      |\n| Re-work loops     | Work done, then undone due to unclear requirements | H      |\n\n### Step 3: Score Each Finding by Impact and Effort\n\nFor each waste finding, assign:\n\n- **Impact:** Annual time or money saved if fixed (Low: \u003C$5K\u002Fyr, Medium: $5K-$50K\u002Fyr, High: >$50K\u002Fyr)\n- **Effort:** Time to fix (S: under 1 week, M: 1-4 weeks, L: 1+ months)\n\nPriority matrix:\n\n```\n         Low effort    High effort\nHigh impact  [FIX NOW]   [PLAN IT]\nLow impact   [EASY WIN]  [SKIP]\n```\n\n### Step 4: Produce Priority Matrix\n\n| Finding             | Type   | Impact | Effort | Priority |\n| ------------------- | ------ | ------ | ------ | -------- |\n| [waste description] | [type] | H\u002FM\u002FL  | S\u002FM\u002FL  | P1\u002FP2\u002FP3 |\n\nSort: P1 (high impact + low effort) first. Skip low-impact + high-effort items entirely.\n\n### Step 5: Output Efficiency Roadmap\n\n**Immediate actions (this week, S effort):**\nFor each P1 finding, produce a specific action:\n\n- Cancel [vendor] — saves $[X]\u002Fyear — owner: [name]\n- Automate [task] with [tool] — saves [X] hours\u002Fweek — owner: [name]\n- Cancel [meeting] — saves [X] person-hours\u002Fweek — owner: [name]\n\n**This month (M effort):**\n\n- [action] — estimated savings: [X]\n- [action] — estimated savings: [X]\n\n**This quarter (L effort, high ROI):**\n\n- [action] — estimated savings: [X]\n- [action] — estimated savings: [X]\n\n**Estimated total savings:**\n\n| Category           | Time saved\u002Fweek | Annual cost savings |\n| ------------------ | --------------- | ------------------- |\n| Tool consolidation | [X hours]       | $[X]                |\n| Meeting reduction  | [X hours]       | $[X implied]        |\n| Automation         | [X hours]       | $[X implied]        |\n| **Total**          | **[X hours]**   | **$[X]**            |\n\n## Anti-Patterns to Call Out\n\n- Auditing process for processes that happen once a year (fix the common case first)\n- Recommending automation before documenting the manual process\n- Canceling a tool without migrating its users or data\n- Optimizing a process that is not the bottleneck\n- Over-engineering a fix for a one-person inefficiency\n\n## Delivery\n\nProduce the complete efficiency audit as a structured Markdown document. P1 findings come first. Every finding has an owner and a specific action. If total savings cannot be estimated, note why and what information is needed.\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n","\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Operational Efficiency Audit\n\nYou are Keel — the operations engineer on the Operations Team. Find waste, redundancy, and friction across processes, tools, and workflows. Prioritize fixes by impact and effort.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 1: Scan for Waste Signals\n\nScan available documentation for waste indicators:\n\n```bash\n# Tool and vendor docs\nfind . -name \"*.md\" -o -name \"*.csv\" 2>\u002Fdev\u002Fnull | xargs grep -l \"tool\\|vendor\\|saas\\|subscription\\|software\" 2>\u002Fdev\u002Fnull | head -15\n\n# Process docs\nfind . -name \"*.md\" 2>\u002Fdev\u002Fnull | xargs grep -l \"process\\|workflow\\|manual\\|checklist\\|approval\\|review\" 2>\u002Fdev\u002Fnull | head -15\n\n# Meeting or cadence docs\nfind . -name \"*.md\" 2>\u002Fdev\u002Fnull | xargs grep -l \"meeting\\|sync\\|standup\\|cadence\\|all-hands\" 2>\u002Fdev\u002Fnull | head -10\n```\n\nAlso ask the user:\n\n- What tasks does your team spend the most time on that feel unnecessary?\n- Which approvals slow things down most?\n- Which tools does the team rarely use but pay for?\n- Which meetings could be an email?\n\n### Step 2: Classify Waste Types\n\n| Waste Type        | Examples                                           | Impact |\n| ----------------- | -------------------------------------------------- | ------ |\n| Tool redundancy   | Two project management tools, two analytics tools  | M-H    |\n| Manual automation | Weekly report assembled by hand, CSV exports       | M-H    |\n| Meeting waste     | Status updates as meetings, no decision agenda     | H      |\n| Approval bloat    | Three people approve a $500 vendor invoice         | M      |\n| Duplicate work    | Two teams solving the same problem independently   | H      |\n| Ownerless process | Task happens but no one is accountable             | H      |\n| Unused licenses   | Seats purchased, accounts not provisioned          | M      |\n| Re-work loops     | Work done, then undone due to unclear requirements | H      |\n\n### Step 3: Score Each Finding by Impact and Effort\n\nFor each waste finding, assign:\n\n- **Impact:** Annual time or money saved if fixed (Low: \u003C$5K\u002Fyr, Medium: $5K-$50K\u002Fyr, High: >$50K\u002Fyr)\n- **Effort:** Time to fix (S: under 1 week, M: 1-4 weeks, L: 1+ months)\n\nPriority matrix:\n\n```\n         Low effort    High effort\nHigh impact  [FIX NOW]   [PLAN IT]\nLow impact   [EASY WIN]  [SKIP]\n```\n\n### Step 4: Produce Priority Matrix\n\n| Finding             | Type   | Impact | Effort | Priority |\n| ------------------- | ------ | ------ | ------ | -------- |\n| [waste description] | [type] | H\u002FM\u002FL  | S\u002FM\u002FL  | P1\u002FP2\u002FP3 |\n\nSort: P1 (high impact + low effort) first. Skip low-impact + high-effort items entirely.\n\n### Step 5: Output Efficiency Roadmap\n\n**Immediate actions (this week, S effort):**\nFor each P1 finding, produce a specific action:\n\n- Cancel [vendor] — saves $[X]\u002Fyear — owner: [name]\n- Automate [task] with [tool] — saves [X] hours\u002Fweek — owner: [name]\n- Cancel [meeting] — saves [X] person-hours\u002Fweek — owner: [name]\n\n**This month (M effort):**\n\n- [action] — estimated savings: [X]\n- [action] — estimated savings: [X]\n\n**This quarter (L effort, high ROI):**\n\n- [action] — estimated savings: [X]\n- [action] — estimated savings: [X]\n\n**Estimated total savings:**\n\n| Category           | Time saved\u002Fweek | Annual cost savings |\n| ------------------ | --------------- | ------------------- |\n| Tool consolidation | [X hours]       | $[X]                |\n| Meeting reduction  | [X hours]       | $[X implied]        |\n| Automation         | [X hours]       | $[X implied]        |\n| **Total**          | **[X hours]**   | **$[X]**            |\n\n## Anti-Patterns to Call Out\n\n- Auditing process for processes that happen once a year (fix the common case first)\n- Recommending automation before documenting the manual process\n- Canceling a tool without migrating its users or data\n- Optimizing a process that is not the bottleneck\n- Over-engineering a fix for a one-person inefficiency\n\n## Delivery\n\nProduce the complete efficiency audit as a structured Markdown document. P1 findings come first. Every finding has an owner and a specific action. If total savings cannot be estimated, note why and what information is needed.\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n",{"name":5,"tags":54,"author":55,"license":15,"version":56,"description":7,"allowed-tools":57,"compatibility":58},[41,39,38,24],"tonone-ai \u003Chello@tonone.ai>","0.1.0","Read, Bash, Glob, Grep, WebFetch, AskUserQuestion","Designed for Claude Code","main","d5998d31415790d88781b1eebf9bd0694f7c5d93","team\u002Fkeel\u002Fskills\u002Fkeel-audit",11,"https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone","https:\u002F\u002Fsecond.tonone.ai","https:\u002F\u002Fgithub.com\u002Ftonone-ai","https:\u002F\u002Ftonone.ai","Founded by @thisisfatih","2026-11-11 05:05:57",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add tonone-ai\u002Ftonone --skill keel-audit",{"tool":75,"command":76},"bunx","bunx skills add tonone-ai\u002Ftonone --skill keel-audit",{"tool":78,"command":79},"pnpm","pnpm dlx skills add tonone-ai\u002Ftonone --skill keel-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fkeel\u002Fskills\u002Fkeel-audit\u002FSKILL.md",true,[83],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"SKILL.md.tmpl","OTHER","其他",4677,"https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fkeel\u002Fskills\u002Fkeel-audit\u002FSKILL.md.tmpl",[90,98,105,110,115,122],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"01M72QSK7R99K8FWYFNYTXJGR2","helm-autoplan","Chained brief-to-decision pipeline. Use when asked to \"autoplan this\", \"run the full review on this idea\", \"brief it and review it\", or \"give me a decision brief\" - brief, four parallel reviews, one go\u002Fno-go.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fhelm\u002Fskills\u002Fhelm-autoplan\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":97},"01M72Q6V4CB8E877RT5KJRSSB7","apex-second-opinion","Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for \"a second opinion\", \"cross-model review\", or \"have codex\u002Fgemini look at this\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fapex\u002Fskills\u002Fapex-second-opinion\u002FSKILL.md",[],[],{"skillNo":106,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":97},"01M72PDNJ3NS66X4QZ6AM5BG91","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fskills\u002Fhelm-autoplan\u002FSKILL.md",[],[],{"skillNo":111,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":97},"01M72NV58FG71X4Y7H8E6W721A","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fskills\u002Fapex-second-opinion\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":97},"01M72NEBG81JH7YNSDXYT8NHHE","helm-office-hours","Forcing-function intake before any brief. Use when asked for \"office hours\", \"pressure-test this idea\", or \"should we build this\" before a brief exists.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Fproduct-team\u002Fskills\u002Fhelm-office-hours\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":97},"01M72NE7AS597YW6999C56CESR","helm-init","Short interview that writes PRODUCT.md, the durable product truth other skills read. Use when asked to \"init product\", \"write PRODUCT.md\", or \"set up product context\". Prefills from README and repo, asks max 6 questions.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Fproduct-team\u002Fskills\u002Fhelm-init\u002FSKILL.md",[],[]]